Summary of Quantifying and Predicting Residential Building Flexibility Using Machine Learning Methods, by Patrick Salter et al.
Quantifying and Predicting Residential Building Flexibility Using Machine Learning Methods
by Patrick Salter, Qiuhua Huang, Paulo Cesar Tabares-Velasco
First submitted to arxiv on: 4 Mar 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Systems and Control (eess.SY)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A novel approach in the field of building energy management proposes two complementary metrics to quantify residential building flexibility, which can be leveraged by aggregators or system operators to optimize grid operations. The study focuses on machine learning-based models for forecasting time-variant and sporadic flexibility at four-hour and 24-hour horizons. Notably, the LSTM model achieves state-of-the-art performance in predicting power flexibility up to 24 hours ahead with an average error of approximately 0.7 kW. However, the model struggles when predicting energy flexibility associated with HVAC systems. This work contributes to a better understanding of building energy management and has implications for grid operations. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Residential buildings use a lot of electricity, accounting for about one-third of all power used in the US. As more people install solar panels or wind turbines on their homes, these buildings can help stabilize the grid. To make this happen, we need to be able to predict when and how much energy they will provide. Right now, most research has focused on commercial buildings, but residential buildings are just as important. This paper proposes new ways to measure a building’s flexibility and uses machine learning to forecast its energy production up to 24 hours in advance. |
Keywords
* Artificial intelligence * Lstm * Machine learning
